arXiv Computation and Language October 28, 2026 By Mingyu Zhang, Zixu Li, Zhiheng Fu, Zhiwei Chen, Jinhe Bi, Yupeng Hu

TrawMem: Reframing Agent Memory as Task-Oriented Role-Adaptive Workspaces

Read the original on arXiv Computation and Language →

TrawMem redefines agent memory systems as Task‑Oriented Role‑Adaptive Workspaces, selecting and organizing memories by their roles in task solving rather than mere relevance. It structures interaction histories into local threads and jointly selects complementary memories to build task‑specific workspaces. Experiments on LoCoMo and MemGallery show consistent macro‑F1 gains of 2.23–3.14 points and improved LLM‑Judge scores with fewer context tokens.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Hugging Face Trending Papers

Jul 15

Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memories to reflective insight stores, access memory through fixed, hand-designed heuristics.

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 16

Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

arXiv:2607. 13591v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.

By Eric Hanchen Jiang, Zhi Zhang, Yuchen Wu, Levina Li, Dong Liu, Xiao Liang, Rui Sun, Yubei Li, Edward Sun, Haozheng Luo, Zhaolu Kang, Aylin Caliskan, Kai-Wei Chang, Ying Nian Wu

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 11

Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents

arXiv:2606. 11680v1 Announce Type: new Abstract: Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input contexts.

By Hao-Lun Hsu, Nikki Lijing Kuang, Boyi Liu, Zhewei Yao, Yuxiong He

llms agents reinforcement-learning

arXiv AI

Jun 16

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.

By Yuyao Wang, Zhongjian Zhang, Mo Chi, Kaichi Yu, Yuhan Li, Miao Peng, Bing Tong, Chen Zhang, Yan Zhou, Jia Li

llms agents benchmarks

arXiv AI

Jun 11

MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback

arXiv:2606. 07909v2 Announce Type: replace Abstract: Modern large language model (LLM) agents can use external tools to help users solve complex tasks.

By Suleyman Armagan Er, Danilo Ribeiro, Yogesh Virkar, Surafel Lakew, Adi Kalyanpur, James Gung, Thomas Delteil, Arshit Gupta

llms agents fine-tuning benchmarks

arXiv AI

Jun 30

Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

arXiv:2507. 05257v4 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component-memory, encompassing how agents memorize, update, and retrieve long-term information-is under-evaluated due to the lack of benchmarks.

By Yuanzhe Hu, Yu Wang, Julian McAuley

llms rag agents benchmarks

One email a morning, machine-written

Related stories

Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback

Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions